README.md

metadata

title: StarSystemClassification
emoji: 🚀
colorFrom: red
colorTo: red
sdk: docker
app_port: 8501
tags:
  - streamlit
pinned: false
short_description: A Streamlit app that predicts of a star system
license: mit

🪐 Star System Classification (LightGBM)

This project predicts the system_type of a star system using astrophysical and galactic features. It is a multiclass classification task with 4 classes (0–3).

✅ What this app does

• Takes 10 input features (numeric + categorical)
• Applies the same preprocessing used in training:
  • stellar_activity_class mapped to numbers (Low/Medium/High)
  • planet_configuration and star_spectral_class encoded using saved LabelEncoders
  • Features are ordered using the saved feature_order file
• Predicts the star system type using a LightGBM model

📦 Files in this repository

Required files (must be in the same folder as app.py):

• app.py
• lightgbm_model.pkl (saved LightGBM model)
• planet_encoder.pkl (LabelEncoder for planet_configuration)
• star_encoder.pkl (LabelEncoder for star_spectral_class)
• featurer.pkl (saved feature order list)
• requirements.txt

🚀 Run locally

pip install -r requirements.txt
streamlit run app.py